Clinical automatic diagnosis and treatment platform for temporomandibular joint disorder

Abstract

The invention discloses a clinical automatic diagnosis and treatment platform for temporomandibular joint disorder, and relates to the field of medical instruments. The platform comprises a patient subjective symptom evaluation system, a clinical diagnosis system, an image diagnosis system and a treatment scheme making system. The patient subjective symptom evaluation system is used for automatically obtaining a subjective feeling diagnosis result of the patient according to a subjective feeling questionnaire filled by the patient; the clinical diagnosis system is used for automatically obtaining a clinical diagnosis result of the patient according to the past medical history and clinical examination of the patient; the image diagnosis system is used for automatically obtaining an image diagnosis result of the patient according to the CBCT image and the MRI image of the patient; the treatment scheme making system is used for automatically making a treatment scheme. According to the platform constructed by the invention, subjective evaluation information of a patient, a clinical automatic diagnosis result and an imaging automatic diagnosis result are fused, a treatment scheme is automatically formulated, temporomandibular joint disorder can be found and diagnosed in time, and influences on treatment such as orthodontic treatment, orthognathic treatment, repair and implantation are avoided.

Description

Technical Field

[0001] This application relates to the field of medical devices, and particularly to a clinical automatic diagnosis and treatment platform for temporomandibular joint disorders. Background Art

[0002] Temporomandibular Disorders (TMD) refers to a general term for many clinical problems that involve the temporomandibular joint or (and) masticatory muscles and have some common symptoms (such as pain, clicking, limited mouth opening, etc.). It is a common and frequently-occurring disease in the oral and maxillofacial region, with an overall prevalence rate of approximately 30%-40%. According to investigations, up to 75% of the population has symptoms or signs of TMD. In addition to causing symptoms such as pain and limited mouth opening, severe cases of TMD can affect the patient's chewing, speech, and other functions, seriously affecting the patient's quality of life and mental health. However, in clinical diagnosis and treatment, a considerable number of patients have no obvious symptoms or signs, but it will affect treatments such as orthodontics, orthognathics, prosthetics, and implantology. Summary of the Invention

[0003] The purpose of this application is to provide a clinical automatic diagnosis and treatment platform for temporomandibular joint disorders to achieve automatic and timely diagnosis of temporomandibular joint disorders and avoid affecting treatments such as orthodontics, orthognathics, prosthetics, and implantology.

[0004] To achieve the above purpose, the following solutions are provided in this application.

[0005] In the first aspect, this application provides a clinical automatic diagnosis and treatment platform for temporomandibular joint disorders, including: a patient subjective symptom assessment system, a clinical diagnosis system, an imaging diagnosis system, and a treatment plan formulation system; the patient subjective symptom assessment system, the clinical diagnosis system, and the imaging diagnosis system are all connected to the treatment plan formulation system; the patient subjective symptom assessment system is used to automatically obtain the patient's subjective symptom diagnosis result according to the subjective feeling questionnaire filled out by the patient; the clinical diagnosis system is used to automatically obtain the patient's clinical diagnosis result according to the patient's past medical history and clinical examination; the imaging diagnosis system is used to automatically obtain the patient's imaging diagnosis result according to the patient's CBCT image and MRI image; the treatment plan formulation system is used to automatically generate the patient's treatment plan according to the patient's subjective symptom diagnosis result, clinical diagnosis result, and imaging diagnosis result.

[0006] According to the specific embodiments provided in this application, the following technical effects are achieved in this application.

[0007] The present application provides a clinical automatic diagnosis and treatment platform for temporomandibular joint disorders. The automatic diagnosis and treatment platform of the present application includes: a patient subjective symptom assessment system, a clinical diagnosis system, an imaging diagnosis system, and a treatment plan formulation system; the patient subjective symptom assessment system is used to automatically obtain the patient's subjective symptom diagnosis result according to the subjective feeling questionnaire filled in by the patient; the clinical diagnosis system is used to automatically obtain the patient's clinical diagnosis result according to the patient's past medical history and clinical examination; the imaging diagnosis system is used to automatically obtain the patient's imaging diagnosis result according to the patient's CBCT image and MRI image; the treatment plan formulation system is used to automatically generate the patient's treatment plan according to the patient's subjective symptom diagnosis result, clinical diagnosis result, and imaging diagnosis result. The platform constructed by the present application integrates the patient's subjective evaluation information, clinical automatic diagnosis result, and imaging automatic diagnosis result to automatically formulate the treatment plan, which can timely detect temporomandibular joint disorders and avoid affecting treatments such as orthodontics, orthognathics, prosthetics, and implantology. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0009] Figure 1 It is a schematic diagram of a clinical automatic diagnosis and treatment platform for temporomandibular joint disorders provided by an embodiment of the present application.

[0010] Figure 2 It is a flowchart of the treatment plan formulation process provided by an embodiment of the present application.

[0011] Figure 3 It is a flowchart of the treatment plan formulation process for irreducible anterior disc displacement provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0013] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0014] The clinical diagnosis and treatment of TMD involve multiple aspects, such as the patient's subjective self-evaluation, clinical examination and diagnosis, imaging examination and diagnosis, treatment plan, etc. The patient's subjective evaluation involves multiple aspects such as pain, mandibular function, depression, and anxiety. Commonly used assessment scales include the Revised Chronic Pain Grade Scale, the Scale of the Impact of Temporomandibular Disorders on Oral Health, the Mandibular Function Limitation Scale-8, and the Depression Anxiety Stress Scale-21. The clinical examination and diagnosis of TMD are based on the Classification and Diagnostic Criteria for Common Temporomandibular Disorders Based on Symptom Questionnaire and Clinical Examination released by the International Association for Dental Research (IADR) in 2014, that is, the DC / TMD diagnostic criteria (diagnostic criteria for temporomandibular disorders). The imaging examination of TMD involves Cone beam computed tomography (CBCT), spiral CT, Magnetic Resonance Imaging (MRI), etc. The formulation of the treatment plan requires comprehensive evaluation based on the patient's medical history, detailed clinical examination, imaging examination results, etc., and a personalized diagnosis and treatment plan is formulated.

[0015] Temporomandibular disorders do not refer to a single disease, but a general term for a group of related diseases. The etiology of TMD is complex and the disease manifestations are diverse, which pose great challenges to the diagnosis and treatment of TMD.

[0016] First of all, the lack of DC / TMD classification diagnostic criteria makes it difficult for many dentists to accurately and comprehensively grasp the condition when facing TMD patients, and thus formulate a personalized diagnosis and treatment plan.

[0017] Secondly, the diagnosis of TMD involves multiple dimensions, including the patient's subjective self-evaluation, clinical examination, imaging examination, etc. However, there is currently a lack of a platform or system that can effectively integrate these diagnostic information. Most studies only focus on one of these aspects. For example, in the aspect of the automatic clinical diagnosis of TMD, existing studies only cover some disease subtypes of TMD and fail to cover all disease types of TMD, limiting its popularization and application in clinical diagnosis and treatment; in the aspect of the imaging diagnosis of TMD, existing studies mostly focus on the identification and diagnosis of single diseases such as temporomandibular joint osteoarthrosis and disc displacement.

[0018] Therefore, there is an urgent need to establish an automatic diagnosis and treatment platform for temporomandibular disorders that can effectively integrate multi-dimensional information such as patient subjective evaluation, clinical diagnosis, imaging diagnosis, and personalized treatment plan, so as to improve the accuracy and comprehensiveness of TMD diagnosis.

[0019] In an exemplary embodiment, a clinical automatic diagnosis and treatment platform for temporomandibular joint disorder is provided. As Figure 1 shown, the platform effectively integrates multi-dimensional information such as patients' subjective evaluations, clinical diagnoses, imaging diagnoses, and personalized treatment plans.

[0020] The platform includes a patients' subjective symptom assessment system, a clinical diagnosis system, an imaging diagnosis system, and a treatment plan formulation system; the patients' subjective symptom assessment system, the clinical diagnosis system, and the imaging diagnosis system are all connected to the treatment plan formulation system;

[0021] The patients' subjective symptom assessment system is used to automatically obtain the diagnostic results of patients' subjective feelings according to the subjective feeling questionnaires filled out by patients;

[0022] The clinical diagnosis system is used to automatically obtain the clinical diagnostic results of patients according to their past medical histories and clinical examinations;

[0023] The imaging diagnosis system is used to automatically obtain the imaging diagnostic results of patients according to their CBCT images and MRI images;

[0024] The treatment plan formulation system is used to automatically generate the treatment plans for patients according to the diagnostic results of patients' subjective feelings, clinical diagnoses, and imaging diagnoses.

[0025] In another exemplary embodiment, in the diagnosis and treatment process of TMD, the subjective evaluation of patients plays a crucial role. This is not only related to the accuracy of diagnosis, but also directly affects the formulation of treatment plans and the evaluation of treatment effects. Clinically, the following scales are often used to evaluate the psychological state of patients.

[0026] The patients' subjective symptom assessment system diagnoses the subjective feelings of patients through the Revised Graded Chronic Pain Scale, the Scale of the Impact of Temporomandibular Disorders on Oral Health, the Mandibular Function Limitation Scale-8, and the Depression, Anxiety and Stress Scale-21 filled out by patients, and preliminarily determines the pain level, psychological state, and degree of life impact, etc.

[0027] Among them, the Revised Graded Chronic Pain Scale (GCPS-R): is an important evaluation tool designed to help doctors and patients more accurately understand and quantify the severity of chronic pain. This scale involves multiple dimensions such as the nature, intensity, duration, and impact on life of pain.

[0028] Oral Health Impact Profile--TMDs (OHIP-TMD): It is a tool specifically used to evaluate the oral health-related quality of life of patients with TMD. This scale covers various oral health problems and related symptoms that TMD patients may encounter, such as pain, functional limitation, chewing difficulty, joint clicking, limited mouth opening, and so on. Through quantitative scoring, patients can more intuitively understand their oral health status and the impact of TMD on daily life.

[0029] Jaw functional limitation scale-8 (JFLS-8): It is a simplified scale specifically used to evaluate the degree of mandibular functional limitation in patients with temporomandibular disorders (TMD). This scale quantitatively evaluates the degree of mandibular functional limitation in TMD patients, helping doctors more intuitively understand the patient's condition and providing important reference for subsequent diagnosis and treatment.

[0030] Depression, anxiety, stress scale-21 (DASS-21): It is a psychological scale widely used in the clinical and research fields. This scale can evaluate the severity of depression, anxiety, and stress symptoms in patients in the past week. Through self-assessment of 21 items, individuals can score each item according to their feelings and experiences, thus obtaining a quantitative index. This index helps professionals and patients themselves understand the current psychological state and provides reference for subsequent psychological intervention and treatment.

[0031] In another exemplary embodiment, the clinical diagnosis system automatically conducts clinical diagnosis by inputting the patient's past medical history and clinical examination by the patient or a professional. This clinical diagnosis system is developed based on the.NET Framework platform and built using the DevExpress control library. The page style is presented in the form of a questionnaire and can automatically output clinical diagnosis results. This clinical diagnosis system includes three modules: a system management module, a data management module, and a DC / TMD diagnosis module.

[0032] System management module: Responsible for the management of all software operation, maintenance, and status-related functions. The specific functions can be further divided into a system configuration module, a log module, and an error handling module.

[0033] Data management module: Mainly used to collect and display patient information and patient data, and to handle the import and export logic of some data. Among them, the main functions include: creating a new patient, editing a patient, importing and exporting data, etc.

[0034] DC / TMD Diagnostic Module: Responsible for collecting diagnostic information and implementing the automatic diagnosis logic. Its main functions include: entering diagnostic information, generating diagnostic results, and exporting diagnostic reports.

[0035] In another exemplary embodiment, imaging examinations play an important role in the diagnosis and treatment of TMD. There are various commonly used examination methods, such as panoramic tomography, CBCT, spiral CT, MRI, etc. Among TMD patients, the most commonly used imaging methods are CBCT and MRI. CBCT is used to evaluate the morphology and bone quality of the condyle and the glenoid fossa, and MRI can evaluate the position of the articular disc, the presence of joint cavity effusion, and bone marrow edema, etc.

[0036] In terms of automatically obtaining the image diagnostic results of the patient based on the patient's CBCT image and MRI image, the image diagnostic system is specifically used for: automatically obtaining the first image diagnostic result of the patient according to the CBCT image; the first image diagnostic result includes the diagnostic results of the condyle state and the glenoid fossa state; automatically obtaining the second image diagnostic result of the patient according to the MRI image; the second image diagnostic result includes the diagnostic results of the articular disc state, synovial state, condyle and glenoid fossa state, the presence of joint cavity effusion, etc.

[0037] In another exemplary embodiment, a method for obtaining the first image diagnostic result is provided, specifically as follows:

[0038] By the patient or a professional entering the patient's CBCT image, the three-dimensional automatic segmentation of the mandible is realized through the Tiny U-Net 3D network model to locate the condyle. The first nnUNet model is used for the two-dimensional automatic segmentation of the condyle and the glenoid fossa. The Pytorch deep learning model automatically outputs the morphological and positional indicators of the condyle and the glenoid fossa based on the segmentation results of the condyle and the glenoid fossa and in combination with the Euclidean distance formula, including the condyle length, condyle width, condyle height, condyle head height; glenoid fossa width, glenoid fossa depth, articular eminence inclination; the position of the condyle in the glenoid fossa in the coronal and sagittal images.

[0039] In another exemplary embodiment, a method for obtaining the first image diagnostic result is provided, specifically as follows:

[0040] By the patient or a professional entering the patient's CBCT image, a first automatic diagnosis model of the temporomandibular joint is constructed based on the YOLOv10 algorithm and in combination with loss functions (including confidence loss function, classification loss function, and bounding box loss function). This model can automatically output the bone quality state of the condyle, that is, whether there is osteoarthrosis. For osteoarthrosis, it further automatically outputs whether there is bone wear, bone hyperplasia, bone sclerosis, and cystic change.

[0041] In another exemplary embodiment, a method for obtaining a first imaging diagnosis result is provided, which is as follows:

[0042] The CBCT images of the patient before and after treatment are input by the patient or a professional. The three-dimensional automatic segmentation of the mandible is performed through the Tiny U-Net3D network. According to the segmentation result, the quantitative calculation of the condyle is automatically carried out, that is, the volumes of the condyle head and the condyle are automatically output. At the same time, for the images before and after treatment, an image registration method based on the mutual information similarity criterion is adopted, and combined with the three-dimensional automatic segmentation result of the mandible, the volume changes of the condyle head and the condyle before and after treatment are automatically output, so as to evaluate whether there is bone repair and remodeling.

[0043] In another exemplary embodiment, a method for obtaining a second imaging diagnosis result is provided, which is as follows:

[0044] The MRI image of the patient is input by the patient or a professional. The second nnUNet model is used to perform two-dimensional automatic segmentation on the condyle, the glenoid fossa and the articular disc. According to the second condyle segmentation image, the second glenoid fossa segmentation image and the articular disc segmentation image, the positions and shapes of the condyle, the glenoid fossa and the articular disc are automatically obtained.

[0045] In another exemplary embodiment, a method for obtaining a second imaging diagnosis result is provided, which is as follows:

[0046] The MRI image of the patient is input by the patient or a professional. A second automatic diagnosis model of the temporomandibular joint is constructed based on the YOLOv10 algorithm and combined with loss functions (including confidence loss function, classification loss function and bounding box loss function). This model can automatically output whether there is osteoarthrosis, whether the articular disc is displaced, whether there is joint effusion, whether the synovium is thickened, etc.

[0047] In another exemplary embodiment, a treatment plan formulation system is used for formulating a personalized treatment plan. This treatment plan formulation system depends on integrating information from multiple dimensions: the subjective feeling diagnosis result of the patient, the clinical diagnosis result, and the imaging diagnosis result. Through artificial intelligence technology, the comprehensive analysis of this information is realized, so as to automatically generate a customized treatment plan that conforms to the individual characteristics of the patient. The working procedure before automatically generating the personalized treatment plan of the patient is as Figure 2 shown. This process aims to ensure that each patient can obtain the most suitable treatment plan for their condition. Specifically, this treatment plan formulation system is implemented through the following steps:

[0048] Multimodal Data Fusion: Integrate the subjective perception diagnosis results of patients (such as pain level, psychological state, etc.), clinical diagnosis results (such as the output of the DC / TMD diagnosis module), and imaging diagnosis results (such as the analysis results of CBCT and MRI). Through data fusion technology, convert data from different sources into a unified format for comprehensive analysis.

[0049] Feature Extraction and Analysis: Use machine learning algorithms to extract features related to treatment plans from the fused data, such as pain degree, psychological state, joint morphological changes, etc. These features will serve as important bases for generating treatment plans.

[0050] Large Language Model-Assisted Decision Making: Use large language models (such as DeepSeek, etc.) to perform descriptive analysis on the patient's condition and provide treatment suggestions in combination with medical knowledge bases. Large language models can understand the patient's condition description through natural language processing technology and generate preliminary treatment plans.

[0051] Personalized Plan Generation: Generate personalized treatment plans based on the prediction results of the model and the suggestions of the large language model, combined with the individual characteristics of the patient. This plan will comprehensively consider factors such as the severity of the patient's condition, psychological state, imaging manifestations, etc., to ensure the accuracy and effectiveness of the treatment plan.

[0052] For each different subtype of TMD, combined with the specific clinical situation of the patient, automatically formulate personalized diagnosis and treatment plans. Taking irreducible disc displacement (a common TMD subtype) as an example, the formulation of the automated personalized treatment plan is as Figure 3 shown.

[0053] According to the specific embodiments provided in this application, this application has the following technical effects.

[0054] The automatic diagnosis and treatment platform for temporomandibular joint disorders of this application can not only significantly improve the diagnosis and treatment efficiency and accuracy of TMD, but more importantly, it helps to avoid potential risks ignored due to temporomandibular joint problems and ensure the smooth progress of oral treatment. In addition, this platform can also widely spread advanced and high-level medical technologies to grass-roots medical institutions and the vast number of oral physicians. This not only helps to narrow the medical level gap between urban and rural areas and regions, but also promotes the balanced development of the entire oral medical industry, enabling more people to enjoy high-quality oral health services.

[0055] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combinations of these technical features do not conflict, they should all be considered as the scope recorded in this specification.

[0056] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on the present application.

Claims

1. A clinical automatic diagnosis and treatment platform for temporomandibular joint disorders, characterized in that, Including: A patient subjective symptom assessment system, a clinical diagnosis system, an imaging diagnosis system, and a treatment plan formulation system; the patient subjective symptom assessment system, the clinical diagnosis system, and the imaging diagnosis system are all connected to the treatment plan formulation system; The patient subjective symptom assessment system is used to automatically obtain the patient's subjective symptom diagnosis result according to the subjective feeling questionnaire filled in by the patient; The clinical diagnosis system is used to automatically obtain the patient's clinical diagnosis result according to the patient's past medical history and clinical examinations; The imaging diagnosis system is used to automatically obtain the patient's imaging diagnosis result according to the patient's CBCT images and MRI images; The treatment plan formulation system is used to automatically generate the patient's treatment plan according to the patient's subjective symptom diagnosis result, clinical diagnosis result, and imaging diagnosis result.

2. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 1, characterized in that, The subjective feeling questionnaire includes: Revised Chronic Pain Grade Scale, Impact of Temporomandibular Disorders on Oral Health Scale, Mandibular Function Limitation Scale-8, and Depression Anxiety Stress Scale-21; the subjective symptom diagnosis result includes: pain grade, psychological state, and degree of life impact.

3. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 1, wherein The clinical diagnosis system is developed based on the.NET Framework platform and built using the DevExpress control library.

4. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 1, characterized in that In terms of automatically obtaining the patient's imaging diagnosis result according to the patient's CBCT images and MRI images, the imaging diagnosis system specifically is used for: Automatically obtaining the patient's first imaging diagnosis result according to the CBCT images; the first imaging diagnosis result includes the diagnosis results of the condyle state and the glenoid fossa state; Automatically obtaining the patient's second imaging diagnosis result according to the MRI images; the second imaging diagnosis result includes the diagnosis results of the articular disc state, synovial membrane state, condyle and glenoid fossa state, and presence or absence of joint cavity effusion.

5. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 4, wherein Automatically obtaining the patient's first imaging diagnosis result according to the CBCT images specifically includes: Using the Tiny U-Net 3D network model to perform three-dimensional segmentation of the mandible on the CBCT images to obtain the position of the condyle; According to the position of the condyle, using the first nnUNet model to perform two-dimensional segmentation of the condyle and glenoid fossa on the CBCT images to obtain the first condyle segmentation image and the first glenoid fossa segmentation image; Obtaining the position and morphology of the condyle and glenoid fossa based on the first condyle segmentation image result and the first glenoid fossa segmentation image result.

6. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 4, characterized in that Automatically obtaining the patient's first imaging diagnosis result according to the CBCT images specifically includes: According to the CBCT images, using the first automatic diagnosis model to automatically obtain the state of the condyle; the state of the condyle includes: presence or absence of bone abrasion, presence or absence of bone hyperplasia, presence or absence of bone sclerosis, and presence or absence of cystic change; the first automatic diagnosis model is a CBCT diagnosis model for the temporomandibular joint, and the first automatic diagnosis model is constructed based on the YOLOv10 network model.

7. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 4, wherein Automatically obtaining the patient's second imaging diagnosis result according to the MRI images specifically includes: Using the second nnUNet model to perform two-dimensional segmentation on the condyle, glenoid fossa, and articular disc to obtain the second condyle segmentation image, the second glenoid fossa segmentation image, and the articular disc segmentation image; Based on the second condyle segmentation image, the second glenoid fossa segmentation image, and the articular disc segmentation image, the positions and morphologies of the condyle, glenoid fossa, and articular disc are automatically obtained. Based on the positions and morphologies of the condyle, glenoid fossa, and articular disc, it is automatically determined whether there is osteoarthrosis and whether the articular disc is displaced.

8. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorder according to claim 4, wherein Based on the MRI image, the second imaging diagnosis result of the patient is automatically obtained, specifically including: Using the second automatic diagnosis model based on the MRI image, the state of the temporomandibular joint is automatically obtained; the state of the temporomandibular joint includes: whether there is osteoarthrosis, whether the articular disc is displaced, whether there is fluid accumulation in the joint cavity, and whether the synovium is thickened; the second automatic diagnosis model is an MRI diagnosis model of the temporomandibular joint, and the second automatic diagnosis model is constructed based on the YOLOv10 network model.

9. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 1, characterized in that In terms of automatically generating a treatment plan for the patient based on the subjective feeling diagnosis result, clinical diagnosis result, and imaging diagnosis result, the treatment plan formulation system is specifically used for: Fusing the subjective feeling diagnosis result, clinical diagnosis result, and imaging diagnosis result to obtain multi-modal fusion data; Using a machine learning algorithm to extract the target features in the multi-modal fusion data; the target features are features related to the treatment plan; Based on the target features, a treatment plan is formulated using a large language model.

10. The clinical automatic diagnosis and treatment platform for temporomandibular joint disorders according to claim 9, characterized in that Based on the target features, a treatment plan is formulated using a large language model, specifically including: Using the large language model to analyze the target features to determine whether the patient has temporomandibular joint disorder and obtain the first judgment result; If the first judgment result is yes, then determine whether treatment is needed by combining the subjective feeling diagnosis result, clinical diagnosis result, and imaging diagnosis result to obtain the second judgment result; If the second judgment result is yes, then combine the subjective feeling diagnosis result, clinical diagnosis result, and imaging diagnosis result to formulate a treatment plan using the large language model and medical knowledge base.

Images